In Silico Pharmacoepidemiologic Evaluation of Drug-Induced Cardiovascular Complications Using Combined Classifiers

Drug-induced cardiovascular complications are the most common adverse drug events and account for the withdrawal or severe restrictions on the use of multitudinous postmarketed drugs. In this study, we developed new in silico models for systematic identification of drug-induced cardiovascular complications in drug discovery and postmarketing surveillance. Specifically, we collected drug-induced cardiovascular complications covering the five most common types of cardiovascular outcomes (hypertension, heart block, arrhythmia, cardiac failure, and myocardial infarction) from four publicly available data resources: Comparative Toxicogenomics Database, SIDER, Offsides, and MetaADEDB. Using these databases, we developed a combined classifier framework through integration of five machine-learning algorithms: logistic regression, random forest, k-nearest neighbors, support vector machine, and neural network. The totality of models included 180 single classifiers with area under receiver operating characteristic curves (AUC) ranging from 0.647 to 0.809 on 5-fold cross-validations. To develop the combined classifiers, we then utilized a neural network algorithm to integrate the best four single classifiers for each cardiovascular outcome. The combined classifiers had higher performance with an AUC range from 0.784 to 0.842 compared to single classifiers. Furthermore, we validated our predicted cardiovascular complications for 63 anticancer agents using experimental data from clinical studies, human pluripotent stem cell-derived cardiomyocyte assays, and literature. The success rate of our combined classifiers reached 87%. In conclusion, this study presents powerful in silico tools for systematic risk assessment of drug-induced cardiovascular complications. This tool is relevant not only in early stages of drug discovery but also throughout the life of a drug including clinical trials and postmarketing surveillance.

[1]  F. Cheng,et al.  Autoimmune Cardiotoxicity of Cancer Immunotherapy. , 2017, Trends in immunology.

[2]  O. Sartor,et al.  Cabazitaxel for castration-resistant prostate cancer – Authors' reply , 2011, The Lancet.

[3]  Yangyang He,et al.  Consensus models for CDK5 inhibitors in silico and their application to inhibitor discovery , 2014, Molecular Diversity.

[4]  Jie Shen,et al.  Adverse Drug Events: Database Construction and in Silico Prediction , 2013, J. Chem. Inf. Model..

[5]  R. Altman,et al.  Data-Driven Prediction of Drug Effects and Interactions , 2012, Science Translational Medicine.

[6]  K. Red-Horse,et al.  Human Induced Pluripotent Stem Cell–Derived Cardiomyocytes as an In Vitro Model for Coxsackievirus B3–Induced Myocarditis and Antiviral Drug Screening Platform , 2014, Circulation research.

[7]  M. Florescu,et al.  Mechanisms and Genetic Susceptibility of Chemotherapy-Induced Cardiotoxicity in Patients With Breast Cancer , 2017, American journal of therapeutics.

[8]  P. Bork,et al.  A side effect resource to capture phenotypic effects of drugs , 2010, Molecular systems biology.

[9]  Thomas C. Wiegers,et al.  The Comparative Toxicogenomics Database: update 2017 , 2016, Nucleic Acids Res..

[10]  Chuang Liu,et al.  Prediction of Drug-Target Interactions and Drug Repositioning via Network-Based Inference , 2012, PLoS Comput. Biol..

[11]  F. Cheng,et al.  Quantitative and systems pharmacology 4. Network-based analysis of drug pleiotropy on coronary artery disease. , 2019, European journal of medicinal chemistry.

[12]  Luhua Lai,et al.  Deep Learning for Drug-Induced Liver Injury , 2015, J. Chem. Inf. Model..

[13]  Jai-Sing Yang,et al.  Endoplasmic reticulum stress contributes to arsenic trioxide‐induced intrinsic apoptosis in human umbilical and bone marrow mesenchymal stem cells , 2016, Environmental toxicology.

[14]  B. Hasinoff,et al.  The lack of target specificity of small molecule anticancer kinase inhibitors is correlated with their ability to damage myocytes in vitro. , 2010, Toxicology and applied pharmacology.

[15]  M. Baccarani,et al.  European LeukemiaNet recommendations for the management and avoidance of adverse events of treatment in chronic myeloid leukaemia , 2016, Leukemia.

[16]  S. George,et al.  Heart Failure: A Paraneoplastic Manifestation of Renal Cell Carcinoma – Reversed With Pazopanib , 2017, Clinical genitourinary cancer.

[17]  V. Soomers,et al.  Fatal heart failure in a young adult female sarcoma patient treated with pazopanib , 2017, Acta oncologica.

[18]  Shujuan Jiang,et al.  Acute myocardial infarction following erlotinib treatment for NSCLC: A case report. , 2016, Oncology letters.

[19]  Tal Lorberbaum,et al.  Coupling Data Mining and Laboratory Experiments to Discover Drug Interactions Causing QT Prolongation. , 2016, Journal of the American College of Cardiology.

[20]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[21]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[22]  J. Yates,et al.  Modeling and Simulation Approaches for Cardiovascular Function and Their Role in Safety Assessment , 2015, CPT: pharmacometrics & systems pharmacology.

[23]  Lei Yang,et al.  Classification of Cytochrome P450 Inhibitors and Noninhibitors Using Combined Classifiers , 2011, J. Chem. Inf. Model..

[24]  S. Lipshultz,et al.  Chemotherapy-induced cardiotoxicity in children , 2017, Expert opinion on drug metabolism & toxicology.

[25]  Heidi Ledford.  Cancer experts unveil wishlist for US government ‘moonshot’ , 2016, Nature.

[26]  M. Kalender,et al.  Could erlotinib treatment lead to acute cardiovascular events in patients with lung adenocarcinoma after chemotherapy failure? , 2015, OncoTargets and therapy.

[27]  Alasdair J. G. Gray,et al.  The IUPHAR/BPS Guide to PHARMACOLOGY in 2018: updates and expansion to encompass the new guide to IMMUNOPHARMACOLOGY , 2017, Nucleic Acids Res..

[28]  J. Hureaux,et al.  Maintenance Treatment by Erlotinib and Toxic Cardiomyopathy: A Case Report , 2016, Oncology.

[29]  Comparative study of microtubule inhibitors--estramustine and natural podophyllotoxin conjugated PAMAM dendrimer on glioma cell proliferation. , 2013, European journal of medicinal chemistry.

[30]  Kaitlyn M. Gayvert,et al.  A Data-Driven Approach to Predicting Successes and Failures of Clinical Trials. , 2016, Cell chemical biology.

[31]  Nicholas P. Tatonetti,et al.  An Integrative Data Science Pipeline to Identify Novel Drug Interactions that Prolong the QT Interval , 2016, Drug Safety.

[32]  E. Matthews,et al.  Prediction of drug-related cardiac adverse effects in humans--A: creation of a database of effects and identification of factors affecting their occurrence. , 2010, Regulatory toxicology and pharmacology : RTP.

[33]  J. Seidman,et al.  Fulminant Myocarditis with Combination Immune Checkpoint Blockade. , 2016, The New England journal of medicine.

[34]  S. Sleijfer,et al.  Incidence and relevance of QTc-interval prolongation caused by tyrosine kinase inhibitors , 2015, British Journal of Cancer.

[35]  S. Polak,et al.  Collation, assessment and analysis of literature in vitro data on hERG receptor blocking potency for subsequent modeling of drugs' cardiotoxic properties , 2009, Journal of applied toxicology : JAT.

[36]  Frederick P. Roth,et al.  Chemical substructures that enrich for biological activity , 2008, Bioinform..

[37]  J. Moslehi,et al.  Cardiovascular Toxic Effects of Targeted Cancer Therapies. , 2016, The New England journal of medicine.

[38]  Chuipu Cai,et al.  Quantitative and Systems Pharmacology. 1. In Silico Prediction of Drug-Target Interactions of Natural Products Enables New Targeted Cancer Therapy , 2017, J. Chem. Inf. Model..

[39]  Sebastian Schneeweiss,et al.  Use of Health Care Databases to Support Supplemental Indications of Approved Medications , 2018, JAMA internal medicine.

[40]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[41]  Pierre Baldi,et al.  Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules , 2013, J. Chem. Inf. Model..

[42]  Vascular safety issues in CML patients treated with BCR/ABL1 kinase inhibitors. , 2015, Blood.

[43]  Donald K. Wedding,et al.  Discovering Knowledge in Data, an Introduction to Data Mining , 2005, Inf. Process. Manag..

[44]  J. Machiels,et al.  Prednisone plus cabazitaxel or mitoxantrone for metastatic castration-resistant prostate cancer progressing after docetaxel treatment: a randomised open-label trial , 2010, The Lancet.

[45]  S. Vallurupalli,et al.  Pazopanib- and bevacizumab-induced reversible heart failure in a patient with metastatic renal cell carcinoma: A case report , 2016, Journal of oncology pharmacy practice : official publication of the International Society of Oncology Pharmacy Practitioners.

[46]  Olivier Bodenreider,et al.  The Unified Medical Language System (UMLS): integrating biomedical terminology , 2004, Nucleic Acids Res..

[47]  CHUN WEI YAP,et al.  PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints , 2011, J. Comput. Chem..

[48]  Nima Milani-Nejad,et al.  Small and large animal models in cardiac contraction research: advantages and disadvantages. , 2014, Pharmacology & therapeutics.

[49]  E. Seront,et al.  Rapid and fatal acute heart failure induced by pazopanib , 2015, BMJ Case Reports.

[50]  Mark R. Davies,et al.  A new classifier-based strategy for in-silico ion-channel cardiac drug safety assessment , 2015, Front. Pharmacol..

[51]  Praveen Shukla,et al.  High-throughput screening of tyrosine kinase inhibitor cardiotoxicity with human induced pluripotent stem cells , 2017, Science Translational Medicine.

[52]  D. Tavian,et al.  Topoisomerases and Anthracyclines: Recent Advances and Perspectives in Anticancer Therapy and Prevention of Cardiotoxicity. , 2017, Current medicinal chemistry.

[53]  Feixiong Cheng,et al.  In silico ADMET prediction: recent advances, current challenges and future trends. , 2013, Current topics in medicinal chemistry.

[54]  J. Irani.  [Sunitinib versus interferon-alpha in metastatic renal-cell carcinoma]. , 2007, Progres en urologie : journal de l'Association francaise d'urologie et de la Societe francaise d'urologie.

[55]  James W Kramer,et al.  Multi-parameter in vitro toxicity testing of crizotinib, sunitinib, erlotinib, and nilotinib in human cardiomyocytes. , 2013, Toxicology and applied pharmacology.

[56]  Thomas Streichert,et al.  Analysis of Tyrosine Kinase Inhibitor-Mediated Decline in Contractile Force in Rat Engineered Heart Tissue , 2016, PloS one.

[57]  K. Hornbuckle,et al.  Evaluation of the Characteristics of Safety Withdrawal of Prescription Drugs from Worldwide Pharmaceutical Markets-1960 to 1999 , 2001 .

[58]  Kashif Ali,et al.  Follow-up of erlotinib related uveitis , 2012, BMJ Case Reports.

[59]  E. Matthews,et al.  Prediction of drug-related cardiac adverse effects in humans--B: use of QSAR programs for early detection of drug-induced cardiac toxicities. , 2010, Regulatory toxicology and pharmacology : RTP.

[60]  Santiago Vilar,et al.  Medicinal chemistry and the molecular operating environment (MOE): application of QSAR and molecular docking to drug discovery. , 2008, Current topics in medicinal chemistry.

[61]  Steven J. M. Jones,et al.  Circos: an information aesthetic for comparative genomics. , 2009, Genome research.

[62]  Jie Li,et al.  Prediction of Polypharmacological Profiles of Drugs by the Integration of Chemical, Side Effect, and Therapeutic Space , 2013, J. Chem. Inf. Model..

[63]  Rob Malouf,et al.  A Comparison of Algorithms for Maximum Entropy Parameter Estimation , 2002, CoNLL.

[64]  Hua Xu,et al.  Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs , 2012, J. Am. Medical Informatics Assoc..

[65]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[66]  J. Dearden,et al.  QSAR modeling: where have you been? Where are you going to? , 2014, Journal of medicinal chemistry.

[67]  Chris Morley,et al.  Open Babel: An open chemical toolbox , 2011, J. Cheminformatics.

[68]  Gisbert Schneider,et al.  Support vector machine applications in bioinformatics. , 2003, Applied bioinformatics.

[69]  Qi Wang,et al.  Discovery of neuroprotective compounds by machine learning approaches , 2016 .

[70]  D. Cox.  The Regression Analysis of Binary Sequences , 2017 .

[71]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[72]  Zhongming Zhao,et al.  Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. , 2014, Journal of the American Medical Informatics Association : JAMIA.

[73]  H. Maddock,et al.  Molecular basis of cancer-therapy-induced cardiotoxicity: introducing microRNA biomarkers for early assessment of subclinical myocardial injury. , 2014, Clinical science.

[74]  K. Aonuma,et al.  Cardiovascular toxic effects of targeted cancer therapy. , 2017, Japanese journal of clinical oncology.

[75]  David S. Wishart,et al.  DrugBank 4.0: shedding new light on drug metabolism , 2013, Nucleic Acids Res..

[76]  H. Korashy,et al.  Molecular mechanisms of cardiotoxicity of gefitinib in vivo and in vitro rat cardiomyocyte: Role of apoptosis and oxidative stress. , 2016, Toxicology letters.